How to integrate Mapbox MCP with Vercel AI SDK v6

This guide walks you through connecting Mapbox to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Mapbox agent that can batch geocode these 10 addresses, get directions from times square to jfk, reverse geocode this latitude and longitude through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Mapbox account through Composio's Mapbox MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Mapbox logoMapbox
Api Key

Mapbox is a platform providing powerful maps, navigation, and location services for developers. Integrate Mapbox for dynamic, interactive mapping and geospatial insights in your apps.

32 Tools

Introduction

This guide walks you through connecting Mapbox to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Mapbox agent that can batch geocode these 10 addresses, get directions from times square to jfk, reverse geocode this latitude and longitude through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Mapbox account through Composio's Mapbox MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Mapbox with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Mapbox integration
  • Using Composio's Tool Router to dynamically load and access Mapbox tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

What is the Mapbox MCP server, and what's possible with it?

The Mapbox MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mapbox account. It provides structured and secure access to your mapping and location data, so your agent can perform actions like geocoding addresses, calculating travel routes, retrieving map embeds, and analyzing travel matrices on your behalf.

  • Batch and individual geocoding: Instantly convert addresses or place names to geographic coordinates—or reverse geocode coordinates to place names—using both batch and individual tools.
  • Route and directions retrieval: Let your agent fetch optimized driving, walking, or cycling directions between waypoints, including turn-by-turn instructions when needed.
  • Distance and travel time analysis: Have the agent generate travel time and distance matrices to compare routes or plan logistics across multiple locations.
  • Map style embed generation: Retrieve ready-to-use embeddable HTML for your custom Mapbox map styles, perfect for sharing or displaying maps in web apps.
  • Permanent geocoding and font data retrieval: Access enterprise-grade, cacheable geocoding data or fetch font glyph ranges for custom rendering and advanced mapping use cases.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["mapbox"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Mapbox tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Mapbox-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Mapbox tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to mapbox, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Mapbox tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Mapbox and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["mapbox"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to mapbox, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Mapbox agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

Every Mapbox action and event your agent gets out of the box.

Batch Geocode V6

Tool to perform batch geocoding with up to 1000 queries in a single request.

Forward Geocode V5

Tool to search for places by name or address using Mapbox Geocoding v5 API (forward geocoding).

Batch Geocoding

Tool to perform batch forward or reverse geocoding for multiple locations.

Forward Geocoding

Tool to convert free-form or structured address into geographic coordinates and place features.

Permanent Forward Geocoding

Tool to perform permanent forward geocoding.

Permanent Reverse Geocoding

Tool to perform permanent reverse geocoding.

Reverse Geocoding

Tool to reverse geocode coordinates into place names.

Get Access Token

Tool to extract and validate Mapbox access token from connection metadata.

Get Isochrone

Tool to calculate areas reachable within a specified amount of time or distance from a location.

Get Map Matching

Tool to snap fuzzy GPS traces to roads on the road network.

Get Optimization V1

Tool to calculate optimal driving routes and trips that visit a set of waypoints.

Get Sprite

Tool to retrieve a sprite image or its JSON document from a Mapbox style.

Get Static Image

Request a static map image from a Mapbox Studio style.

Get Static Tiles

Tool to retrieve raster tiles from a Mapbox Studio style.

Get Token Information

Tool to retrieve information about a Mapbox access token and validate its status.

Get Vector Tiles

Tool to retrieve vector tiles from Mapbox-hosted vector tilesets.

Map Matching (POST)

Tool to snap GPS coordinates to the road network using POST method for longer coordinate lists.

Query Tile Features

Tool to retrieve data about specific features from vector tilesets based on a location.

Request Style Embed HTML

Retrieve embeddable HTML for a Mapbox style that can be embedded in an iframe.

Retrieve Directions

Tool to retrieve directions between waypoints.

Retrieve Font Glyph Ranges

Tool to retrieve font glyph ranges as PBF tiles.

Retrieve Marker

Tool to retrieve a standalone marker image without any background map.

Retrieve Matrix

Retrieve a travel time and distance matrix between multiple locations.

Retrieve Searchbox Place Details

Tool to retrieve full details for a specific place by its Mapbox ID.

Retrieve Style

Retrieves the complete Mapbox style specification as JSON, including all layers, sources, sprites, and configuration.

Retrieve Style WMTS

Retrieve a WMTS (Web Map Tile Service) capabilities document for a Mapbox style.

Retrieve Tileset Metadata

Tool to retrieve metadata for a Mapbox tileset.

Reverse Geocoding V6

Tool to convert geographic coordinates to place names using Geocoding v6 API.

Search Box Reverse Geocoding

Tool to convert coordinates to places using the Search Box API (reverse geocoding).

Search Box Forward

Tool to search for places by name or address using the Search Box API.

Search by Category

Tool to search for places by category (e.

Search Box Suggest

Tool to get autocomplete suggestions for a partial search query.

FAQ

Frequently asked questions

With a standalone Mapbox MCP server, the agents and LLMs can only access a fixed set of Mapbox tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Mapbox and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Mapbox tools.

Yes, absolutely. You can configure which Mapbox scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Mapbox data and credentials are handled as safely as possible.

Start with Mapbox.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Mapbox tool your agent needs.Free to start.

Start building